What is root-cause-priority?

A decision framework for sorting several connected problems into root causes and surface symptoms. It distinguishes the underlying problem from later effects, while allowing urgent blockages to take priority.

Use it to trace cause-and-effect chains, rank fixes, and balance urgent symptoms against important underlying problems. It is intended for groups of related issues, not one simple standalone question.

It helps when fixing one visible issue may leave the cause untouched, or when many related problems compete for attention. It provides a way to decide what to address first.

root-cause-priority — Skill for Claude Code by dhicoc

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add dhicoc/wuyun-liuqi-skills --skill root-cause-priority

Clone the repo

git clone --depth 1 https://github.com/dhicoc/wuyun-liuqi-skills

Made for: Claude Code.

Or install wuyun-liuqi-skills, the plugin that ships this one along with the rest of its 38 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/root-cause-priority/github.svg)](https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/root-cause-priority)

Your own site

<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/root-cause-priority"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/root-cause-priority/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dhicoc/wuyun-liuqi-skills/root-cause-priority"><img src="https://agentmods.dev/badge/skills/dhicoc/wuyun-liuqi-skills/root-cause-priority.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,660 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.01660
Opus 5.5	$0.00030	$0.00664
Sonnet 5.5	$0.00015	$0.00332
Haiku 4.5	$0.00007	$0.00166

Measured 2mo ago against content hash a0d8a1a2d1d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

root-cause-priority scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

scripts/lib/neijing_snapshot/lingshu/root-cause-priority/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

标本根结定位法

R — 原文 (Reading)

先病而后逆者治其本, 先逆而后病者治其本。先病而后生中满者治其标, 先中满而后烦心者治其本。病发而有余, 本而标之; 病发而不足, 标而本之。能知六经标本者, 可以无惑于天下。

— 黄帝/岐伯, 病本第二十五、卫气第五十二

I — 方法论骨架 (Interpretation)

标本根结定位法是一个区分问题源头与末端, 据此确定干预优先级的决策框架。

识别标本: 在因果链中, 先发生的/根本原因是"本", 后发生的/继发症状是"标"。在空间上, 源头(四肢末端/根)是本, 末端(头面胸腹/结)是标。
缓急定序: 默认"治本"优先, 但有明确的例外——"中满"(急症/关键瓶颈)和"大小便不利"(功能受阻)必须先治标。急则治标, 缓则治本。
虚实影响排序: "病发而有余(实), 本而标之"——从本治起;"病发而不足(虚), 标而本之"——从标治起。虚证时系统承受力弱, 需要先缓解表面症状再追根溯源。
间甚并行: "间者并行, 甚者独行"——问题不太严重时可以标本同治, 问题严重时只能集中精力治一个。

A1 — 书中的应用 (Past Application)

案例 1: 先病后逆的治本原则

问题: 先得病后出现气逆, 该治哪个?
方法论的使用: "先病而后逆者治其本"——原发病是本, 气逆是标(继发), 治原发病则气逆自消。
结论: 症状的出现顺序揭示了因果链, 先治因后治果。
结果: 治本则标自消, 避免了在继发症状上浪费精力。

案例 2: 中满的紧急优先

问题: 先得病后出现中满(腹部胀满), 按理应治本, 但中满很急, 怎么办?
方法论的使用: "先病而后生中满者治其标"——虽然中满是标(继发), 但它阻塞了核心通道, 必须先解决。
结论: 当标证(继发问题)威胁到系统核心功能时, 标的优先级临时提升。
结果: 先解决紧急阻塞, 再回头治本。

A2 — 触发场景 (Future Trigger) ★

多问题纠缠: 面对一堆相互关联的问题, 不知道从哪个入手。
因果链追溯: 知道表现但不确定根因, 需要沿因果链回溯。
先治标还是先治本: 紧急问题(标)和根本问题(本)同时存在, 需要排序。

语言信号

"问题太多了, 不知道先解决哪个"
"根本原因到底是什么"
"紧急的和重要的怎么平衡"
"解决了A, B又冒出来了"

与相邻 skill 的区分

与 excess-deficiency-decision 的区别: 虚实补泻解决"方向(补/泻)", 标本根结解决"顺序(先/后)"。两者独立但经常串联。
与 timing-opportunity 的区别: 标本根结是"做什么的优先级", 时机选择是"何时做的时机窗口"。

E — 可执行步骤 (Execution)

列出所有问题并建立因果链
- 列出所有问题, 标注相互之间的因果关系(A导致B, B导致C)。
- 完成标准: 有明确的因果链图, 标注了时间先后顺序。
区分标本
- 在因果链中: 先发生的/根本原因=本, 后发生的/继发表现=标。
- 完成标准: 每个问题标注了"本"或"标", 并说明判断依据。
检查紧急例外
- 是否存在"中满型"问题——虽然不是根因, 但阻塞了核心功能, 必须先解决?
- 完成标准: 识别并标注紧急例外, 给出优先级调整理由。
确定执行顺序
- 默认从本治起; 有紧急例外则先治标; 虚证时从标治起。
- 完成标准: 给出明确的执行顺序和每步的理由。

B — 边界 (Boundary) ★

不要在以下情况使用

问题孤立: 如果问题之间没有因果关系, 标本框架无法展开。
教条治本: 不是所有情况都应该"先治本", 紧急情况必须先治标。

失败模式

本标混淆: 把症状当原因, 在标上浪费精力而本持续恶化。
教条主义: 无论多急都坚持"先治本", 忽视了紧急标证的威胁。

作者的盲点

灵枢的标本主要关注时间先后和虚实, 现代问题还可能涉及资源约束、利益相关方优先级等额外维度, 需要扩展框架。

Read the full file on GitHub · 123 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 123 lines · 75 tokens per session scan A a0d8a1a2d1d0

Subscribe to this mod's changes

root-cause-priority is a skill published in the GitHub repository dhicoc/wuyun-liuqi-skills (52 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,660 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging Planning 公众号

root-cause-priority next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
root-cause-prioritydhicoc/wuyun-liuqi-skills	Skill	52	2mo ago	MIT	A	75	Claude Code
alert-sopPM-Shawn/Abu-Cowork	Skill	419	today	Apache-2.0	A	20	Claude Code
code-runnerzhinjs/zhin	Skill	137	yesterday	MIT	A	87	Claude Code, Codex
workflow-recoverymrpulor-gh/nuphus	Skill	89	yesterday	Apache-2.0	A	0	Claude Code, Codex
runtime-diagnosticszhinjs/zhin	Skill	137	yesterday	MIT	A	13	Claude Code, Codex
metago-developer-responsemetago-ai/metagolifeform	Skill	6	yesterday	MIT	A	78	Claude Code, Codex
metago-problem-tracemetago-ai/metagolifeform	Skill	6	yesterday	MIT	A	54	Claude Code, Codex